A hybrid BiLSTM and rule-based system for integrated diabetes prediction and personalized guidance
Muhammad Saleem, Muhammad Hamid, Saadia Malik · 2026
Read A hybrid BiLSTM and rule-based system for integrated diabetes prediction and personalized guidance by Muhammad Saleem, Muhammad Hamid, Saadia Malik (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0347672.txt.
Description
Muhammad Saleem, Muhammad Hamid, and Saadia Malik built a diabetes system that does two jobs: predict who likely has the disease and then give personal lifestyle guidance. Most prediction tools stop at the diagnosis. Their system pairs a deep learning model that reads patterns in health data with a rule-based engine that turns the result into advice.
The prediction model was trained on a merged dataset cleaned with care to avoid leaking answers into training. It beat seven standard machine learning models and other deep learning designs under ten-fold cross-checking. For patients, the guidance half is the point: a risk score alone changes nothing, while tailored steps for food and activity might.
Catalog record
| CREATOR | Muhammad Saleem, Muhammad Hamid, Saadia Malik |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33239 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |